Internet of Things Intrusion Detection System
Joseph Bamidele Awotunde, Abdulrauf Olarenwaju Babatunde, Rasheed Gbenga Jimoh, Dayo Reuben · 2024
The Internet of Things (IoT) intrusion detection system (IDS) is a comprehensive study that explores various artificial intelligence (AI), deep learning (DL), and machine learning (ML) techniques to safeguard IoT networks. It aims to develop robust systems capable of identifying and mitigating potential cyber threats and intrusions within interconnected IoT devices and networks. An IDS is a system that detects unauthorized access to or activities on an IoT network or device and alerts the user to its presence. Therefore, this chapter presents a systematic study of AI, DL, and ML approaches that can be used for the purpose of developing an IDS for the IoT. AI and DL are two of the most prominent and widely used technologies employed in the modern security landscape. By conducting a comprehensive review of related works, this chapter provides a holistic view of IoT IDSs and the associated security challenges. Furthermore, this chapter also presents state-of-the-art algorithms and approaches used for design and development of advanced IoT IDSs. The chapter compares the different methods and techniques that can be used to enable an IDS for IoT and discusses the challenges that arise due to the inherent complexity of the task. The results of the study are expected to be useful for researchers in the field of cybersecurity who are interested in designing and developing secure IoT IDSs. Finally, we discuss the implications of the findings as well as the future research directions that can be pursued in this area. We conclude that AI, DL, and ML methods can be effectively used to enable an IDS for the IoT while maintaining an adequate level of accuracy, performance, and scalability.